System and method for multi-modal graph-based personalization

    公开(公告)号:US11301774B2

    公开(公告)日:2022-04-12

    申请号:US15593353

    申请日:2017-05-12

    申请人: NEC Europe Ltd.

    摘要: A method for learning latent representations of individual users in a personalization system uses a graph-based machine learning framework. A graph representation is generated based on input data in which the individual users are each represented by a node. The nodes are associated with labels. Node vector representations are learned by combining label latent representations from a vertex and neighboring nodes so as to reconstruct the label latent representation of the vertex and updating the label latent representations of the neighboring nodes using gradients resulting from application of a reconstruction loss. A classifier/regressor is trained using the node vector representations and the node vector representations are mapped to personalizations. Actions associated with the personalizations are then initiated.

    METHOD FOR PERFORMING DISTRIBUTED GEOGRAPHIC EVENT PROCESSING AND GEOGRAPHIC EVENT PROCESSING SYSTEM
    4.
    发明申请
    METHOD FOR PERFORMING DISTRIBUTED GEOGRAPHIC EVENT PROCESSING AND GEOGRAPHIC EVENT PROCESSING SYSTEM 有权
    执行分布式地理事件处理和地理事件处理系统的方法

    公开(公告)号:US20160212584A1

    公开(公告)日:2016-07-21

    申请号:US14913693

    申请日:2013-10-24

    申请人: NEC EUROPE LTD.

    发明人: Tobias JACOBS

    IPC分类号: H04W4/02 H04L29/08

    摘要: A method for performing distributed geographic event processing includes: defining a geographical state system for a universe of locations that includes a model specifying a state transition function and a global aggregation function; providing a local state system for a subset of the universe of locations being defined as a single-machine implementation of the geographical state system; providing a local aggregation function being defined as an implementation of the global aggregation function of the geographical state system; and creating, via a processor, distributed scalable deployments that implement the geographical state system by dividing the universe of locations geographically among different computational nodes and by instantiating on each of the computational nodes an instance of the local state system and the local aggregation function conforming to the subset of the universe of locations assigned to the respective computational node.

    摘要翻译: 一种用于执行分布式地理事件处理的方法包括:为包括指定状态转换函数和全局聚集函数的模型定义用于一个整体位置的地理状态系统; 为被定义为地理状态系统的单机实现的位置宇宙的子集提供本地状态系统; 提供本地聚合功能,定义为地理状态系统的全局聚合功能的实现; 以及通过处理器创建分布式可扩展部署,其通过在不同的计算节点之间划分地理位置上的位置的Universe并且通过在每个计算节点上实例化本地状态系统的实例和符合 分配给相应计算节点的位置的子集。

    Method for operating a wireless network, a wireless network and a device
    5.
    发明授权
    Method for operating a wireless network, a wireless network and a device 有权
    用于操作无线网络,无线网络和设备的方法

    公开(公告)号:US09338686B2

    公开(公告)日:2016-05-10

    申请号:US14006760

    申请日:2012-01-13

    摘要: Method for operating a wireless network, wherein at least one MIMO (Multiple Input Multiple Output) group of different stations will be constructed by a grouping algorithm based on a grouping metric for providing a MIMO group of different stations addressable simultaneously in space by a base station using MIMO techniques and meeting a definable level of performance quality, the grouping metric being based on an SINR (Signal-to-Interference and Noise Ratio) experienced by each station within the MIMO group. The method includes: computing an SNR (Signal-to-Noise Ratio) that a new station would experience without any interference when added to an existing MIMO group; computing an SINR estimate by correcting the SNR with the sum of spatial correlations between the new and each of the stations already present in the existing MIMO group; and using the SINR estimate for deciding whether the new station can be added to the existing MIMO group.

    摘要翻译: 一种用于操作无线网络的方法,其中通过分组算法将通过分组度量来构建不同站的至少一个MIMO(多输入多输出)组,所述分组度量用于提供基站同时在空间中寻址的不同站的MIMO组 使用MIMO技术并满足可定义的性能水平,分组度量基于MIMO组内每个站经历的SINR(信号与干扰和噪声比)。 该方法包括:当添加到现有的MIMO组时,计算新的站将经历没有任何干扰的SNR(信噪比); 通过利用已经存在于现有MIMO组中的新站和每个站之间的空间相关性之和校正SNR来计算SINR估计; 并且使用SINR估计来确定新站是否可以被添加到现有的MIMO组。

    Method for monitoring traffic in a network and a network
    6.
    发明授权
    Method for monitoring traffic in a network and a network 有权
    监控网络和网络流量的方法

    公开(公告)号:US09338075B2

    公开(公告)日:2016-05-10

    申请号:US13500653

    申请日:2009-10-09

    IPC分类号: G06F15/173 H04L12/26

    CPC分类号: H04L43/12 H04L43/026

    摘要: For providing a simple monitoring mechanism with reduced resource and performance requirements a method for monitoring traffic in a network is claimed, wherein a monitoring activity of at least two monitoring probes of the network is coordinated by a coordinating element, wherein at least two nodes of the network are able to operate as coordinating elements and wherein the responsibility for coordinating the monitoring activity of the monitoring probes is split between the nodes according to a compressed representation of flow parameter keys. Further, an according network is described, preferably for carrying out the above mentioned method.

    摘要翻译: 为了提供具有降低的资源和性能要求的简单监视机制,要求保护网络中的流量的方法,其中网络的至少两个监视探测器的监视活动由协调元件协调,其中,至少两个节点 网络能够作为协调元件操作,并且其中根据流量参数键的压缩表示在监视探测器之间协调监视活动的责任在节点之间分割。 此外,描述了优选用于执行上述方法的相关网络。

    Method and a system for distributing of user equipment context in an evolved packet system
    7.
    发明授权
    Method and a system for distributing of user equipment context in an evolved packet system 有权
    用于在演进分组系统中分发用户设备上下文的方法和系统

    公开(公告)号:US09313642B2

    公开(公告)日:2016-04-12

    申请号:US14008670

    申请日:2012-04-05

    申请人: Gottfried Punz

    发明人: Gottfried Punz

    摘要: A method for distributing user equipment context in an evolved packet system, including a plurality of user equipment, at least one eNodeB, a first mobility management entity and a second mobility management entity and one serving gateway connected to the first and second mobility management entity, the plurality of user equipment being connected via one of the eNodeBs to the second mobility management entity and to the serving gateway, wherein the user equipment context for the plurality of user equipment is each stored at the second mobility management entity, includes: a) transferring bulk user equipment context for the plurality of user equipment context, each having a mobility management entity code, to the first mobility management entity, b) reconfiguring the mobility management entity codes, c) storing the transferred user equipment context in the first mobility management entity, and d) transferring reconfigured mobility management entity codes to the at least one eNodeB.

    摘要翻译: 一种用于在演进的分组系统中分发用户设备上下文的方法,包括多个用户设备,至少一个eNodeB,第一移动性管理实体和第二移动性管理实体以及连接到第一和第二移动性管理实体的一个服务网关, 所述多个用户设备经由所述eNodeB中的一个连接到所述第二移动性管理实体和所述服务网关,其中,所述多个用户设备的所述用户设备上下文每个存储在所述第二移动性管理实体,包括:a)传送 每个具有移动性管理实体代码的多个用户设备上下文的批量用户设备上下文给第一移动性管理实体,b)重新配置移动性管理实体代码,c)将所传送的用户设备上下文存储在第一移动性管理实体中 以及d)将重配置的移动性管理实体代码传送到所述至少一个eNodeB。

    Method and system for probabilistic processing of data using a bit matrix, tuples, and hash values
    9.
    发明授权
    Method and system for probabilistic processing of data using a bit matrix, tuples, and hash values 有权
    使用位矩阵,元组和哈希值对数据进行概率处理的方法和系统

    公开(公告)号:US09305265B2

    公开(公告)日:2016-04-05

    申请号:US13498943

    申请日:2010-09-29

    IPC分类号: G06F17/00 G06N7/00 H04L29/06

    CPC分类号: G06N7/005 H04L63/0227

    摘要: A method for probabilistic processing of data, wherein the data is provided in form of a data set S composed of multidimensional n-tuples of the form (x1, . . . , xn), is characterized in that an n-dimensional data structure is generated by way of providing a bit matrix, providing a number K of independent hash functions Hk that are employed in order to address the bits in the matrix, and inserting the n-tuples (x1, . . . , xn) into the bit matrix by computing the hash values Hk(x) for all values x of the n-tuple for each of the number K of independent hash functions Hk, and by setting the resulting bits [Hk(x1), . . . , Hk(xn)] of the matrix. Furthermore, a respective system is disclosed.

    摘要翻译: 一种用于对数据进行概率处理的方法,其中以由形式(x1,...,xn)的多维n元组组成的数据集S的形式提供数据,其特征在于,n维数据结构是 通过提供位矩阵生成,提供数字K的独立散列函数Hk,以便对矩阵中的位进行寻址,并将n元组(x1,...,xn)插入位矩阵 通过对独立散列函数Hk的数量K中的每一个计算散列值H k(x),并且通过设置所得到的比特[Hk(x1))来计算针对n元组的所有值x的散列值H k(x)。 。 。 ,Hk(xn)]。 此外,公开了相应的系统。

    Method for operating an openflow switch within a network, an openflow switch and a network
    10.
    发明授权
    Method for operating an openflow switch within a network, an openflow switch and a network 有权
    用于操作网络内的开流开关的方法,开流开关和网络

    公开(公告)号:US09253098B2

    公开(公告)日:2016-02-02

    申请号:US14003524

    申请日:2011-03-07

    摘要: For allowing a very flexible scheduling of data flows within an OpenFlow (OF) switch a method for operating an OpenFlow switch within a network includes using the OpenFlow switch to direct arriving data flows out of different ports of the OpenFlow switch. The method is characterized in that a scheduling mechanism for performing at least one scheduling task is assigned to the OpenFlow switch, wherein a metric will be used to assign weights to the arriving data flows and wherein the data flows will then be scheduled based on the assigned weights and based on a scheduling policy. Further, a corresponding OpenFlow switch and a corresponding network are described, preferably for carrying out the above mentioned method.

    摘要翻译: 为了允许在OpenFlow(OF)交换机内进行非常灵活的数据流调度,用于在网络中操作OpenFlow交换机的方法包括使用OpenFlow交换机将到达的数据流引导到OpenFlow交换机的不同端口。 该方法的特征在于,用于执行至少一个调度任务的调度机制被分配给OpenFlow交换机,其中将使用度量来对到达的数据流分配权重,并且其中然后将基于所分配的数据流来调度数据流 权重并基于调度策略。 此外,描述了相应的OpenFlow交换机和相应的网络,优选地用于执行上述方法。